WEEK3

R Markdown

library(tidyverse)

## ── Attaching core tidyverse packages ──────────────────────── tidyverse 2.0.0 ──
## ✔ dplyr     1.1.4     ✔ readr     2.1.5
## ✔ forcats   1.0.0     ✔ stringr   1.5.1
## ✔ ggplot2   3.5.2     ✔ tibble    3.3.0
## ✔ lubridate 1.9.4     ✔ tidyr     1.3.1
## ✔ purrr     1.1.0     
## ── Conflicts ────────────────────────────────────────── tidyverse_conflicts() ──
## ✖ dplyr::filter() masks stats::filter()
## ✖ dplyr::lag()    masks stats::lag()
## ℹ Use the conflicted package (<http://conflicted.r-lib.org/>) to force all conflicts to become errors

library(janitor)

## 
## Attaching package: 'janitor'
## 
## The following objects are masked from 'package:stats':
## 
##     chisq.test, fisher.test

# Load CSV directly from Downloads
hci_raw <- read_csv("/Users/yj/Downloads/HCI1.csv", 
                    col_types = cols(.default = "c"),  # treat all columns as character
                    locale = locale(encoding = "UTF-8"))

# Clean column names
hci_raw <- clean_names(hci_raw)

# Quick check
glimpse(hci_raw)

## Rows: 7
## Columns: 15
## $ series_name  <chr> "Human Capital Index (HCI) (scale 0-1)", "Human Capital I…
## $ series_code  <chr> "HD.HCI.OVRL", "HD.HCI.OVRL", NA, NA, NA, NA, NA
## $ country_name <chr> "Italy", "Israel", NA, NA, NA, NA, NA
## $ country_code <chr> "ITA", "ISR", NA, NA, NA, NA, NA
## $ x2010_yr2010 <chr> "0.750265836715698", "0.718269050121307", NA, NA, NA, NA,…
## $ x2011_yr2011 <chr> "..", "..", NA, NA, NA, NA, NA
## $ x2012_yr2012 <chr> "..", "..", NA, NA, NA, NA, NA
## $ x2013_yr2013 <chr> "..", "..", NA, NA, NA, NA, NA
## $ x2014_yr2014 <chr> "..", "..", NA, NA, NA, NA, NA
## $ x2015_yr2015 <chr> "..", "..", NA, NA, NA, NA, NA
## $ x2016_yr2016 <chr> "..", "..", NA, NA, NA, NA, NA
## $ x2017_yr2017 <chr> "0.769", "0.763", NA, NA, NA, NA, NA
## $ x2018_yr2018 <chr> "0.752880394458771", "0.763064444065094", NA, NA, NA, NA,…
## $ x2019_yr2019 <chr> "..", "..", NA, NA, NA, NA, NA
## $ x2020_yr2020 <chr> "0.727819681167603", "0.733995318412781", NA, NA, NA, NA,…

library(dplyr)
library(tidyr)

hci_long <- hci_raw %>%
  pivot_longer(
    cols = starts_with("x"),      # year columns after clean_names()
    names_to = "year",
    values_to = "hci"
  ) %>%
  mutate(
    year = as.integer(gsub("x|_yr.*", "", year)),  # extract numeric year
    hci = as.numeric(hci)                          # convert '..' to NA
  ) %>%
  filter(country_name %in% c("Israel", "Italy"),
         year >= 2010, year <= 2020)

## Warning: There was 1 warning in `mutate()`.
## ℹ In argument: `hci = as.numeric(hci)`.
## Caused by warning:
## ! NAs introduced by coercion

# Average HCI per country
avg_hci <- hci_long %>%
  group_by(country_name) %>%
  summarise(avg_hci = mean(hci, na.rm = TRUE))
avg_hci

## # A tibble: 2 × 2
##   country_name avg_hci
##   <chr>          <dbl>
## 1 Israel         0.745
## 2 Italy          0.750

# Line chart
library(ggplot2)
ggplot(hci_long, aes(x = year, y = hci, color = country_name)) +
  geom_line(size = 1.2) +
  geom_point(size = 2) +
  labs(title = "Human Capital Index (2010–2020): Israel vs Italy",
       x = "Year", y = "HCI (0–1)", color = "Country") +
  theme_minimal()

## Warning: Using `size` aesthetic for lines was deprecated in ggplot2 3.4.0.
## ℹ Please use `linewidth` instead.
## This warning is displayed once every 8 hours.
## Call `lifecycle::last_lifecycle_warnings()` to see where this warning was
## generated.

## Warning: Removed 14 rows containing missing values or values outside the scale range
## (`geom_point()`).

This is an R Markdown document. Markdown is a simple formatting syntax for authoring HTML, PDF, and MS Word documents. For more details on using R Markdown see http://rmarkdown.rstudio.com.

When you click the Knit button a document will be generated that includes both content as well as the output of any embedded R code chunks within the document. You can embed an R code chunk like this:

Note that the echo = FALSE parameter was added to the code chunk to prevent printing of the R code that generated the plot.